A Caltech Library Service

Multi-Label Learning from Single Positive Labels

Cole, Elijah and Aodha, Oisin Mac and Lorieul, Titouan and Perona, Pietro and Morris, Dan and Jojic, Nebojsa (2021) Multi-Label Learning from Single Positive Labels. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ, pp. 933-942. ISBN 978-1-6654-4509-2.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for multi-label classification. When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image. Furthermore, in some settings detection is intrinsically difficult e.g. finding small object instances in high resolution images. As a result, multi-label training data is often plagued by false negatives. We consider the hardest version of this problem, where annotators provide only one relevant label for each image. As a result, training sets will have only one positive label per image and no confirmed negatives. We explore this special case of learning from missing labels across four different multi-label image classification datasets for both linear classifiers and end-to-end fine-tuned deep networks. We extend existing multi-label losses to this setting and propose novel variants that constrain the number of expected positive labels during training. Surprisingly, we show that in some cases it is possible to approach the performance of fully labeled classifiers despite training with significantly fewer confirmed labels.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2021 IEEE. This project was supported in part by an NSF Graduate Research Fellowship (Grant No. DGE1745301) and the Microsoft AI for Earth program. We would also like to thank Jennifer J. Sun, Matteo Ruggero Ronchi, and Joseph Marino for helpful feedback.
Funding AgencyGrant Number
NSF Graduate Research FellowshipDGE-1745301
Microsoft AI for EarthUNSPECIFIED
Record Number:CaltechAUTHORS:20220105-995282700
Persistent URL:
Official Citation:E. Cole, O. M. Aodha, T. Lorieul, P. Perona, D. Morris and N. Jojic, "Multi-Label Learning from Single Positive Labels," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 933-942, doi: 10.1109/CVPR46437.2021.00099
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:112729
Deposited By: Tony Diaz
Deposited On:09 Jan 2022 21:28
Last Modified:09 Jan 2022 21:28

Repository Staff Only: item control page